Robust Physical-World Attacks on Deep Learning Visual Classification

Eykholt, Kevin; Evtimov, Ivan; Fernandes, Earlence; Li, Bo; Rahmati, Amir; Xiao, Chaowei; Prakash, Atul; Kohno, Tadayoshi; Song, Dawn

doi:10.1109/cvpr.2018.00175

Cited by 1,755 publications

(1,248 citation statements)

References 36 publications

Supporting

Mentioning

1,242

Contrasting

Unclassified

Order By: Relevance

“…For instance, regarding a supervised ML classification model, adversarial attacks try to discover the minimum changes that should be applied to the input data in order to cause a different classification. This has happened regarding computer vision systems of autonomous vehicles; a minimal change in a stop signal, imperceptible to the human eye, led vehicles to detect it as a 45 mph signal [359]. For the particular case of DL models, available solutions such as Cleverhans [360] seek to detect adversarial vulnerabilities, and provide different approaches to harden the model against them.…”

Section: Explanations For Ai Security: Xai and Adversarial Machine Lementioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if harnessed appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in Machine Learning, the entire community stands in front of the barrier of explainability, an inherent problem of the latest techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI (namely, expert systems and rule based models). Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models. The overview presented in this article examines the existing literature and contributions already done in the field of XAI, including a prospect toward what is yet to be reached. For this purpose we summarize previous efforts made to define explainability in Machine Learning, establishing a novel definition of explainable Machine Learning that covers such prior conceptual propositions with a major focus on the audience for which the explainability is sought. Departing from this definition, we propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at explaining Deep Learning methods for which a second dedicated taxonomy is built and examined in detail. This critical literature analysis serves as the motivating background for a series of challenges faced by XAI, such as the interesting crossroads of data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to the field of XAI with a thorough taxonomy that can serve as reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

show abstract

Section: Explanations For Ai Security: Xai and Adversarial Machine Lementioning

confidence: 99%

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Adversarial attacks can have serious implications in many security-related applications as well as in the physical world. For example, in 2018, Eykholt et al showed that placing small stickers on traffic signs (here: stop signs) can induce a misclassification rate of 100% in lab settings and 85% in a field test where video frames captured from a moving vehicle [172].…”

Section: Adversarial Learningmentioning

confidence: 99%

Machine Learning in Python: Main Developments and Technology Trends in Data Science, Machine Learning, and Artificial Intelligence

2020

View full text Add to dashboard Cite

Smarter applications are making better use of the insights gleaned from data, having an impact on every industry and research discipline. At the core of this revolution lies the tools and the methods that are driving it, from processing the massive piles of data generated each day to learning from and taking useful action. Deep neural networks, along with advancements in classical ML and scalable general-purpose GPU computing, have become critical components of artificial intelligence, enabling many of these astounding breakthroughs and lowering the barrier to adoption. Python continues to be the most preferred language for scientific computing, data science, and machine learning, boosting both performance and productivity by enabling the use of low-level libraries and clean high-level APIs. This survey offers insight into the field of machine learning with Python, taking a tour through important topics to identify some of the core hardware and software paradigms that have enabled it. We cover widely-used libraries and concepts, collected together for holistic comparison, with the goal of educating the reader and driving the field of Python machine learning forward.

show abstract

“…So the linear term of has zero expectation, and the quadratic term is directly dependent on variance of noise and the trace of Hessian. As a convex relaxation, if we assume • f 0 is convex, then we have that d · A max ≥ Tr(A) ≥ A max for A ∈ S d×d + , we can rewrite (9) as…”

Section: Mathematical Explanationsmentioning

confidence: 99%

Towards Robust Neural Networks via Random Self-ensemble

Liu

Cheng

Zhang

et al. 2018

Lecture Notes in Computer Science

328

264

View full text Add to dashboard Cite

Recent studies have revealed the vulnerability of deep neural networks: A small adversarial perturbation that is imperceptible to human can easily make a well-trained deep neural network misclassify. This makes it unsafe to apply neural networks in security-critical applications. In this paper, we propose a new defense algorithm called Random Self-Ensemble (RSE) by combining two important concepts: randomness and ensemble. To protect a targeted model, RSE adds random noise layers to the neural network to prevent the strong gradient-based attacks, and ensembles the prediction over random noises to stabilize the performance. We show that our algorithm is equivalent to ensemble an infinite number of noisy models f without any additional memory overhead, and the proposed training procedure based on noisy stochastic gradient descent can ensure the ensemble model has a good predictive capability. Our algorithm significantly outperforms previous defense techniques on real data sets. For instance, on CIFAR-10 with VGG network (which has 92% accuracy without any attack), under the strong C&W attack within a certain distortion tolerance, the accuracy of unprotected model drops to less than 10%, the best previous defense technique has 48% accuracy, while our method still has 86% prediction accuracy under the same level of attack. Finally, our method is simple and easy to integrate into any neural network.

show abstract

Robust Physical-World Attacks on Deep Learning Visual Classification

Cited by 1,755 publications

References 36 publications

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Machine Learning in Python: Main Developments and Technology Trends in Data Science, Machine Learning, and Artificial Intelligence

Towards Robust Neural Networks via Random Self-ensemble

Contact Info

Product

Resources

About